Or

4
Tutorials that teach
Line Chart

Take your pick:

Tutorial

Source: Tables and graphs created by the author

In this tutorial, you're going to learn about line charts, which are a display that we can use their distribution for quantitative data. So we can display our quantitative data in a line chart, and the construction is very similar to a histogram. There's a separate tutorial on how to construct histograms.

So suppose that we have an elementary school class in Muncie, Indiana, say, keeping track of the high temperatures each day for the days that they're in school. In Indiana, it might get down to, say, zero degrees Fahrenheit, or highs of maybe 90 degrees at the beginning of the year in September or at the end of the year in May. And so suppose that their distribution looked something like this.

10 days of the year, the temperature was in the zeros, it was between zero and 10 degrees. It was single digits. Here, the number started with one, it was 10 to 19.9 degrees. Here, it started with two, et cetera.

The histogram for it looks like this. Between zero and 10, there were 10 days the did that. Between 10 and 20 there were 16 days that did that, et cetera.

To create a line chart, what we do is we take those heights of the bars, and instead of creating them as heights of bars, create dots instead. The heights are indicated with a dot. Then we get rid of the boxes, and the dots are connected.

This is a line graph, and it's almost the same visual display is the histogram showed. Also, like with histograms, binning makes a difference. If we bin differently than by tens, we're going to be going from this many dots, to more dots.

But the dots won't be so up high as they are right now. This is what it looks like when you bin by five degrees instead of 10 degrees. Finally, if you put the histogram and the line chart on the same set of axes, you can create something called a frequency polygon.

That's when you have the histogram and the line chart together, and you connect the tops of the midpoints-- the midpoint of the tops of each box. It's also possible to do multiple line charts on the same set of axes. This is really helpful, because it's not really all that possible to do that with a histogram.

So suppose that a school in Tucson, Arizona did the same project as the kids in Muncie, Indiana did, and then they share their information. Maybe the Arizona data looked like this. A lot more warmer days, days in the 70s, 80s, and 90s. And I suppose the '60s we're all very common, and not so much in Indiana.

The line charts, then, can be compared, and you see that on the line charts. That days in the 60s, 70s, 80s, 90s, and even 100s were very common. Whereas in Indiana, the days of our most common we're days in the 30s, and 40s, and 50s.

And so to recap, line charts are nice way to visualize quantitative data. It's much the same construction as a histogram, but the heights are determined by dots and set of boxes. The best use of a line chart is when you can compare a couple of different line charts on the same set of axes.

So the terms we used were line chart and frequency polygon, which is when it's used in the same location as a histogram. Good luck and we'll see you next time.